← All work

Technology Digest · 2026 – present

Production AI for a mental-health platform

Role: Sole ML Engineer

>99% of traffic resolved in <100 ms
~99.7% crisis-detection accuracy
5.4× cheaper than external APIs

The problem

Sole ML engineer on a safety-critical product with zero ML infrastructure, where a wrong answer has real consequences.

The approach

  • Built 12 production systems from scratch: LLM serving with vLLM behind a stable API, a multi-tier real-time crisis-detection cascade, WHO/NICE-aligned clinical note generation, multilingual semantic search, and LLM intent routing, with adversarial safety evaluation and permanent regression harnesses.

The impact

  • >99% of traffic resolved in <100 ms
  • ~99.7% crisis-detection accuracy
  • 5.4× cheaper than external APIs

Stack

vLLMFastAPIPyTorchSentence-TransformersDockerAWS

Want to see it working?

Run the live demo, or send an inquiry to talk about your version of this.